Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1081 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.2348. Min Act: -0.0000

Data Index: 337436 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.2199. Min Act: -0.0000

Data Index: 829304 (The Pile)

Max Activating Token Index: 117

Text #2

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0616. Min Act: -0.0000

Data Index: 1610867 (The Pile)

Max Activating Token Index: 762

Text #3

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1317261 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1800832 (The Pile)

Max Activating Token Index: 325

Text #5

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1844341 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1562468 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.8923. Min Act: -0.0000

Data Index: 78871 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1981326 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1570689 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1643381 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1839406 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1844996 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.8241. Min Act: -0.0000

Data Index: 518624 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1799023 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.8097. Min Act: -0.0000

Data Index: 8571 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1162725 (The Pile)

Max Activating Token Index: 444

Text #17

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.6838. Min Act: -0.0000

Data Index: 24713 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.7155. Min Act: -0.0000

Data Index: 781722 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1474607 (The Pile)

Max Activating Token Index: 163